Perbandingan Algoritma Decision Tree, ID3, dan Random Forest dalam Klasifikasi Faktor-Faktor yang Mempengaruhi Karier Mahasiswa Ilmu Komputer

Abstract

This study aims to compare the performance of three classification algorithms, namely Decision Tree, ID3, and Random Forest, in identifying factors that influence the careers of computer Science students. These algorithms are applied to a dataset that includes various student attributes, such as GPA, programming skills, and completed projects. The results show that Random Forest provides more accurate and stable prediction results than Decision Tree and ID3, especially in reducing the risk of overfitting. Students with high skills in Python and SQL and who focus on software development tend to choose a career in Software Engineering. While those involved in AI/ML-based projects tend to choose Data Science. The conclusions of this study provide valuable insights for educational institutions to design more effective career development strategies for students.